Emanuele Neri MD, Moderator: Research Consultant, General Electric Company Research Consultant, Bracco Group

Hiroyuki Yoshida PhD, Moderator: Patent holder, Hologic, Inc Patent holder, MEDIAN Technologies

1) Understand needs of CAD in radiologic image interpretation. 2) Understand basic concept of CAD in assisting radiologists' image reading. 3) Understand the usefulness of CAD in improving radiologists' performance. 4) Learn historical review of CAD developments. 5) Learn CAD for detection and differential diagnosis of common cancers. 6) Learn ROC analysis of radiologists' performance without and with CAD in observer studies.

Computer-aided diagnosis (CAD) has become one of the major research subjects in medical imaging and diagnostic radiology. In this refresher course, the principles of CAD will be presented together with current development and clinical applications. The CAD is aimed at improving the radiologists diagnostic accuracy, and can be used as primary, concurrent or second reader. The latter is the recommended paradigm. In principle the CAD performs a morphological recognition of the ;pathology; (nodule, focal lesion, polyp, etc) combined with quantitative information (MR signal intensity, CT density, contrast enhancement, volume, etc. Many different types of CAD schemes are being developed for detection and/or characterization of various lesions in different imaging modalities, including conventional projection radiography, CT, MRI, and ultrasound imaging. Organs that are subjected to research for CAD include the breast, lung, colon, brain, liver, kidney, and the vascular and skeletal systems. For detection of breast cancer on mammograms, many commercial CAD systems have been used clinically in assisting radiologists worldwide. For detection of lung cancer, CAD schemes have been developed for detection of pulmonary nodules on chest radiographs and CT images. In addition, CAD schemes have been developed for differential diagnosis of distinction between malignant and benign lesions. For colon cancer, CAD schemes have been developed for detection of polyps in CT colonography. Observer performance studies with use of ROC analysis indicated an improved performance in radiologists.

www.rad.unipi.itwww.massgeneral3dimaging.org

Neri, E, Yoshida, H, Computer Aided Diagnosis (Development and Clinical Applications).  Radiological Society of North America 2014 Scientific Assembly and Annual Meeting, - ,Chicago IL. http://archive.rsna.org/2014/14001878.html